الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Adversarial patches can disrupt Vision-Language-Action (VLA) models by manipulating visual observations, leading to failures in robot control. However, it remains poorly understood which internal mechanisms underlie these failures and how targeted interventions can mitigate them. In this work, we mechanistically analyze VLA representations using a sparse autoencoder (SAE) and identify a feature whose activation strongly correlates with the presence of an adversarial patch. Based on this analysis, we suppress the identified feature at inference time only when a linear probe detects an attack. This intervention improves robustness without the cost of fine-tuning the VLA. We evaluate our method against VLA adversarial patch attacks on LIBERO-10. Conditional intervention improves success rate under intermittent attacks, whereas continuously applying the same intervention substantially degrades policy performance. These results show that attack-related internal representations can provide useful targets for VLA adversarial defense and that controlling when to intervene is important for limiting disruption to nominal policy behavior.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Horiba, Y., Aoki, K., Yasuki, S., Kim, B. J., & Miyanishi, T. (2026). الكشف والقمع: دفاع آلي ضد البقع العدائية في نماذج VLA. https://omanscience.com/ar/articles/detect-and-suppress-a-mechanistic-defense-against-adversarial-patches-in-vla-models
MLA 9
Horiba, Yukiya, et al. "الكشف والقمع: دفاع آلي ضد البقع العدائية في نماذج VLA." https://omanscience.com/ar/articles/detect-and-suppress-a-mechanistic-defense-against-adversarial-patches-in-vla-models.
شيكاغو (المؤلف–التاريخ)
Horiba, Yukiya, Koshiro Aoki, Shunsuke Yasuki, Bum Jun Kim, and Taiki Miyanishi. 2026. "الكشف والقمع: دفاع آلي ضد البقع العدائية في نماذج VLA." https://omanscience.com/ar/articles/detect-and-suppress-a-mechanistic-defense-against-adversarial-patches-in-vla-models.
هارفارد
Horiba, Y., Aoki, K., Yasuki, S., Kim, B. J. and Miyanishi, T. (2026) 'الكشف والقمع: دفاع آلي ضد البقع العدائية في نماذج VLA', Available at: https://omanscience.com/ar/articles/detect-and-suppress-a-mechanistic-defense-against-adversarial-patches-in-vla-models.
فانكوفر
Horiba Y, Aoki K, Yasuki S, Kim BJ, Miyanishi T. الكشف والقمع: دفاع آلي ضد البقع العدائية في نماذج VLA. https://omanscience.com/ar/articles/detect-and-suppress-a-mechanistic-defense-against-adversarial-patches-in-vla-models
IEEE
Y. Horiba, K. Aoki, S. Yasuki, B. J. Kim, and T. Miyanishi, "الكشف والقمع: دفاع آلي ضد البقع العدائية في نماذج VLA," https://omanscience.com/ar/articles/detect-and-suppress-a-mechanistic-defense-against-adversarial-patches-in-vla-models.